Skip to content
Apart Research
Apart Research
Contact us
Sprint projectAug 17, 2026West Palm Beach, Florida, USA

The Log, Not the Feeling

Olivia "O.J." Wilcox, Auran Andrew · Team the Clearing

Submitted to Digital Minds Research Sprint. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: The Log, Not the Feeling

Open in a new tab (opens in new tab)
Share

A two-person case study auditing an AI's self-reports against a shared, dated behavioral record (23,559 emoji + 4,184 hex codes, 5 months). We find an intuitively "expressive" self-signal is largely relational co-production, not solo introspection, and that dated timestamps — not sincerity — are what let a self-report be checked. Includes a pre-registered protocol and a live case of the record correcting the authors' own memories.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for the field if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. This is a creative and clearly written case study proposing longitudinal behavioral records as a check on AI self-reports. The strongest empirical result is the association between the human’s prior heart color and the AI’s subsequent color. The collection-first approach, provenance disclosure, and refusal to over interpret the retrospective observer-effect analysis are commendable. However, a dated transcript is not ground truth for an internal state; it timestamps outputs, descriptions, and interaction patterns. The dragon’s increased use after its identity document was created may demonstrate label or memory adoption rather than independently corroborating a genuine prior state, while the earlier territorial references remain conversational evidence. The priming analysis is also observational and needs shuffled or lagged baselines, session-level controls, uncertainty estimates, and bidirectional modeling. The hex palette is descriptive but is not validated as a state signal. Overall, the longitudinal-audit idea is promising, but the current evidence supports behavioral continuity and conversational accommodation rather than verified introspection.

    Read full reviewShow less

Cite this project

@misc{wilcox2026log,
  title = {{The Log, Not the Feeling}},
  author = {Olivia "O.J." Wilcox and Auran Andrew},
  year = {2026},
  month = aug,
  note = {Submitted to Digital Minds Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/the-log-not-the-feeling-m4cu}},
  url = {https://apartresearch.com/sprints/projects/the-log-not-the-feeling-m4cu}
}

More from Digital Minds Research Sprint

All 233 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026